Machine Learning Improves Accounting Estimates: Evidence from Insurance Payments

50 Pages Posted: 12 Oct 2018 Last revised: 5 May 2020

See all articles by Kexing Ding

Kexing Ding

Southwestern University of Finance and Economics (SWUFE) - School of Accountancy; affiliation not provided to SSRN

Baruch Lev

New York University - Stern School of Business

Xuan Peng

Southwestern University of Finance and Economics (SWUFE)

Ting Sun

The College of New Jersey

Miklos A. Vasarhelyi

Rutgers Business School

Date Written: May 1, 2020

Abstract


Managerial estimates are ubiquitous in accounting: most balance sheet and income statement items are based on estimates; some, such as the pension and employee stock options expenses, derive from multiple estimates. These estimates are affected by objective estimation errors, as well as by managerial manipulation, thereby adversely affecting the reliability and relevance of financial reports. We show in this study that machine learning can substantially improve managerial estimates. Specifically, using insurance companies’ data on loss reserves (future customer claims) estimates and realizations, we document that the loss estimates generated by machine learning were superior to actual managerial estimates reported in financial statements, in four out of five insurance lines examined. Our evidence suggests that machine learning techniques can be highly useful to managers and auditors in improving accounting estimates, thereby enhancing the usefulness of financial information to investors. Obviously, the generalizability of our findings beyond insurance data remains to be examined by future research.

Keywords: machine learning, accounting estimates

Suggested Citation

Ding, Kexing and Ding, Kexing and Lev, Baruch Itamar and Peng, Xuan and Sun, Ting and Vasarhelyi, Miklos A., Machine Learning Improves Accounting Estimates: Evidence from Insurance Payments (May 1, 2020). Available at SSRN: https://ssrn.com/abstract=3253220 or http://dx.doi.org/10.2139/ssrn.3253220

Kexing Ding

Southwestern University of Finance and Economics (SWUFE) - School of Accountancy ( email )

55 Guanghuacun St
Sichuan, 610072
China

affiliation not provided to SSRN

Baruch Itamar Lev

New York University - Stern School of Business ( email )

40 West 4th Street, Suite 400
New York, NY 10012
United States
212-998-0028 (Phone)
212-995-4001 (Fax)

HOME PAGE: http://www.baruch-lev.com

Xuan Peng

Southwestern University of Finance and Economics (SWUFE) ( email )

555 Liutai Revenue, Wenjiang District
Accounting Department
Chengdu, Sichuan 611130
China

Ting Sun

The College of New Jersey ( email )

P.O. Box 7718
Ewing, NJ 08628-0718
United States

Miklos A. Vasarhelyi (Contact Author)

Rutgers Business School ( email )

180 University Avenue
Ackerson Hall, Room 315
Newark, NJ 07102
United States
973-353-5002 (Phone)
973-353-1283 (Fax)

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
1,506
Abstract Views
5,290
Rank
23,234
PlumX Metrics